LONDON, UK, 31 July 2018 — AMFG, a UK-based provider of workflow automation software for additive manufacturing, today unveiled a new Holistic Build Analysis tool that allows manufacturers to instantly estimate how full a machine build is — without the need for nesting. This marks the latest addition to the company’s AI-powered software platform and will enable users to predict how cost-effective a part will be to produce.
Further expanding its auto-scheduling capabilities, AMFG’s Holistic Build Analysis tool uses machine learning technology to provide users with an alternative, virtually instantaneous, way to estimate the capacity of their builds without having to go through the nesting process.
“Our new build analysis feature offers significant time savings for manufacturers,” explained Felix Doerr, Head of Business Development at AMFG. “Many nesting software packages offer an iterative solution, requiring users to set time limits before the nesting process is completed. This is an incredibly time-consuming process, particularly if you merely need an estimate of how full your builds are for production scheduling purposes.
“With Holistic Build Analysis, instead of waiting hours to see how full your build is, our customers can receive an accurate capacity estimation in only a matter of seconds. Our new tool is a radical alternative not only in terms of the time savings it delivers, but also because of its potential it has to change the way we optimise production scheduling for additive manufacturing.”
Being able to predict the capacity of a machine build can help companies prioritise production jobs and streamline the production planning process. Currently, manufacturers must use nesting software to achieve this — a time-consuming process that can take hours or even days to complete.
With AMFG’s production management system, users can assign parts to a build, after which machine learning algorithms are used to generate an estimate of the build’s fill rate almost instantaneously. Given as a percentage, users can then use this data to prioritise the parts that should be produced next, for example, based on deadlines, machine availability or the optimal arrangement of parts.
“Our customers will be able to compare requested parts by volume and geometrical parameters to see where they fit best on the build,” says Doerr. “Soon, the system will even be able to suggest which parts should be produced next.
“Our software’s estimations are becoming ever-more accurate thanks to our algorithms. Over time, we anticipate that automated build analysis and scheduling will become an integrated part of the end-to-end manufacturing process, taking additive manufacturing another step closer to a fully automated, autonomous manufacturing future.”